US-12620066-B2 - Systems and methods for computed tomography image denoising with a bias-reducing loss function

Abstract

Systems and methods for computed tomography imaging are provided. In one embodiment, a method includes acquiring an image, inputting the image to a machine learning model to generate a denoised image, the machine learning model trained with a loss function that weights variance differently from bias, and outputting the denoised image. In this way, structural details in denoised CT images may be improved while maintaining textural information in the denoised images.

Inventors

• Madhuri Mahendra NAGARE
• Roman Melnyk
• Obaidullah Rahman
• Ken Sauer
• Charles Bouman, Jr.

Assignees

• GE Precision Healthcare LLC
• PURDUE RESEARCH FOUNDATION
• UNIVERSITY OF NOTRE DAME DU LAC

Dates

Publication Date

20260505

Application Date

20220505

Claims (15)

1. 1 . A method, comprising: acquiring an image; inputting the image to a machine learning model to generate a denoised image, the machine learning model trained with a bias-reducing loss function that approximates a loss function that weights variance differently from bias by applying a bias-reducing parameter to the variance, wherein training the machine learning model with the bias-reducing loss function includes calculating a bias-reduced loss for a ground truth image based on a corresponding bias-reduced estimate image and the ground truth image, the bias-reduced estimate image generated based on a weighted combination of denoised images output by the machine learning model, the weighted combination weighted based on the bias-reducing parameter; and outputting the denoised image.
2. 2 . The method of claim 1 , further comprising receiving a user selection of the bias-reduction parameter, wherein the bias-reducing parameter is a value that is greater than zero and less than one.
3. 3 . The method of claim 1 , wherein the machine learning model comprises a convolutional neural network.
4. 4 . The method of claim 3 , further comprising training the machine learning model with a residual training strategy.
5. 5 . The method of claim 1 , wherein acquiring the image comprises controlling a computed tomography (CT) imaging system to acquire the image.
6. 6 . The method of claim 1 , wherein outputting the denoised image comprises displaying, via a display device, the denoised image, wherein the denoised image includes image texture and detail of the image with a reduced amount of image noise relative to the image.
7. 7 . A method, comprising: acquiring an image; inputting the image to a machine learning model to generate a denoised image, the machine learning model trained with a loss function that weights variance differently from bias by applying a bias-reducing parameter to the variance; and outputting the denoised image, wherein, during training of the machine learning model, the loss function computes an error between a weighted average of two or more enhanced images and a ground truth image, and further comprising, during training of the machine learning model, generating two or more noisy images from the ground truth image according to two or more independent noise realizations.
8. 8 . The method of claim 7 , further comprising, during training of the machine learning model, inputting the two or more noisy images to the machine learning model to generate the two or more enhanced images.
9. 9 . The method of claim 7 , wherein the loss function computes a first error between a first weighted average of the two or more enhanced images and the ground truth image, and a second error between a second weighted average of the two or more enhanced images and the ground truth image.
10. 10 . A system, comprising: an image processing device communicatively coupled to a medical imaging system and storing instructions in non-transitory memory, the instructions executable to: acquire, via the medical imaging system, an image; input the image to a machine learning model stored in the non-transitory memory to generate a denoised image, the machine learning model trained with a loss function that weights variance differently from bias by calculating a bias-reduced loss for a ground truth image based on a corresponding bias-reduced estimate image and the ground truth image, the bias-reduced estimate image generated based on a weighted combination of denoised images output by the machine learning model, the weighted combination weighted by applying a bias-reducing parameter; and output the denoised image.
11. 11 . The system of claim 10 , wherein the image processing device further stores instructions in the non-transitory memory, the instructions executable to receive a user selection of the bias-reduction parameter.
12. 12 . The system of claim 10 , wherein the image processing device further stores instructions in the non-transitory memory, the instructions executable to, during training of the machine learning model, generate two or more noisy images from the ground truth image according to two or more independent noise realizations.
13. 13 . The system of claim 12 , wherein the image processing device further stores instructions in the non-transitory memory, the instructions executable to, during training of the machine learning model, input the two or more noisy images to the machine learning model to generate the denoised images.
14. 14 . The system of claim 10 , wherein the bias-reduced loss includes a first error between a first weighted average of the denoised images and the ground truth image, and a second error between a second weighted average of the denoised images and the ground truth image.
15. 15 . The system of claim 10 , wherein the medical imaging system comprises a computed tomography imaging system, and wherein the loss function weights the variance differently from the bias to reduce bias in the denoised image while increasing variance in the denoised image.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS The present application claims priority to U.S. Provisional Patent Application No. 63/185,960, entitled “SYSTEMS AND METHODS FOR COMPUTED TOMOGRAPHY IMAGE DENOISING WITH A BIAS-REDUCING LOSS FUNCTION,” and filed May 7, 2021, the entire contents of which is hereby incorporated by reference for all purposes. FIELD Embodiments of the subject matter disclosed herein relate to medical imaging, and more particularly to image denoising for computed tomography imaging. BACKGROUND Computed tomography (CT) may be used as a non-invasive medical imaging technique. Specifically, CT imaging data acquisition may include passing X-ray beams through an object, such as a patient, such that the X-ray beams are attenuated and then collecting the attenuated X-ray beams at an X-ray detector array. The acquired CT imaging data may be a set of line integral measurements corresponding to a distribution of attenuation coefficients of the object. The distribution may be reconstructed from the set of line integral measurements as a viewable image via a backprojection, or backward projection, step in an analytical or an iterative reconstruction algorithm. BRIEF DESCRIPTION In one embodiment, a method may include acquiring an image, inputting the image to a machine learning model to generate a denoised image, the machine learning model trained with a loss function that weights variance differently from bias, and outputting the denoised image. In this way, the structural and textural details in denoised CT images may be improved while denoising the images. It should be understood that the brief description above is provided to introduce in simplified form a selection of concepts that are further described in the detailed description. It is not meant to identify key or essential features of the claimed subject matter, the scope of which is defined uniquely by the claims that follow the detailed description. Furthermore, the claimed subject matter is not limited to implementations that solve any disadvantages noted above or in any part of this disclosure. BRIEF DESCRIPTION OF THE DRAWINGS The present disclosure will be better understood from reading the following description of non-limiting embodiments, with reference to the attached drawings, wherein below: FIG. 1 shows a pictorial view of an exemplary medical imaging system, according to an embodiment; FIG. 2 shows a schematic block diagram of the exemplary medical imaging system, according to an embodiment; FIG. 3 shows a schematic block diagram of an exemplary medical image processing system, according to an embodiment; FIG. 4 shows a graph illustrating a tradeoff between bias and variance for a bias-reducing loss function in contrast with a conventional mean squared error loss function, according to an embodiment; FIG. 5 shows a graph illustrating a relationship between bias-reduction parameters, according to an embodiment; FIG. 6 shows a block diagram illustrating an example architecture for training a neural network configured for image denoising with a bias-reducing loss function, according to an embodiment; FIG. 7 shows a high-level flow chart illustrating an example method for training a neural network for image denoising with a bias-reducing loss function, according to an embodiment; FIG. 8 and FIG. 9 show a set of images illustrating example image denoising with neural network with a bias-reducing loss function, according to an embodiment; FIG. 10 shows a set of images illustrating example image denoising with neural networks trained with a bias-reducing loss function for different bias-reduction parameters, according to an embodiment; and FIG. 11 is a flow chart illustrating a method for denoising an image with a trained denoising model, according to an embodiment. DETAILED DESCRIPTION The following description relates to various embodiments of medical imaging systems. In particular, systems and methods are provided for bias-reduced image denoising for computed tomography (CT) imaging systems. One such medical imaging system configured to acquire CT medical imaging data is depicted in FIGS. 1 and 2, while an image processing system for denoising CT images is depicted in FIG. 3. There is growing interest in the use of deep neural network (DNN)-based image denoising to reduce the x-ray dosage for patients in medical CT. For example, noise reduction methods based on convolutional neural networks (CNNs) enable a reduction in x-ray dosage of a patient while achieving similar image quality. Mean squared error (MSE) loss functions are typically used for DNN training because they result in a trained network that approximately maximizes the peak signal-to-noise ratio (PSNR). However, MSE loss functions in DNN training weight errors due to bias and variance equally, but the error due to bias is typically more egregious because the bias error results in the loss of image texture and detail. In other words, the MSE loss function tends to produce den